mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 21:30:07 +06:00
dd9d483d03
* doc
* [tests] Add sample files for a regression task
* [HUGE] Trainer
* Feedback from @sshleifer
* Feedback from @thomwolf + logging tweak
* [file_utils] when downloading concurrently, get_from_cache will use the cached file for subsequent processes
* [glue] Use default max_seq_length of 128 like before
* [glue] move DataTrainingArguments around
* [ner] Change interface of InputExample, and align run_{tf,pl}
* Re-align the pl scripts a little bit
* ner
* [ner] Add integration test
* Fix language_modeling with API tweak
* [ci] Tweak loss target
* Don't break console output
* amp.initialize: model must be on right device before
* [multiple-choice] update for Trainer
* Re-align to 827d6d6ef0
127 lines
4.2 KiB
Python
127 lines
4.2 KiB
Python
# coding=utf-8
|
|
# Copyright 2018 HuggingFace Inc..
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
|
|
import argparse
|
|
import logging
|
|
import sys
|
|
import unittest
|
|
from unittest.mock import patch
|
|
|
|
import run_generation
|
|
import run_glue
|
|
import run_language_modeling
|
|
import run_squad
|
|
|
|
|
|
logging.basicConfig(level=logging.DEBUG)
|
|
|
|
logger = logging.getLogger()
|
|
|
|
|
|
def get_setup_file():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("-f")
|
|
args = parser.parse_args()
|
|
return args.f
|
|
|
|
|
|
class ExamplesTests(unittest.TestCase):
|
|
def test_run_glue(self):
|
|
stream_handler = logging.StreamHandler(sys.stdout)
|
|
logger.addHandler(stream_handler)
|
|
|
|
testargs = [
|
|
"run_glue.py",
|
|
"--data_dir=./examples/tests_samples/MRPC/",
|
|
"--task_name=mrpc",
|
|
"--do_train",
|
|
"--do_eval",
|
|
"--output_dir=./examples/tests_samples/temp_dir",
|
|
"--per_gpu_train_batch_size=2",
|
|
"--per_gpu_eval_batch_size=1",
|
|
"--learning_rate=1e-4",
|
|
"--max_steps=10",
|
|
"--warmup_steps=2",
|
|
"--overwrite_output_dir",
|
|
"--seed=42",
|
|
"--max_seq_length=128",
|
|
]
|
|
model_name = "--model_name_or_path=bert-base-uncased"
|
|
with patch.object(sys, "argv", testargs + [model_name]):
|
|
result = run_glue.main()
|
|
del result["loss"]
|
|
for value in result.values():
|
|
self.assertGreaterEqual(value, 0.75)
|
|
|
|
def test_run_language_modeling(self):
|
|
stream_handler = logging.StreamHandler(sys.stdout)
|
|
logger.addHandler(stream_handler)
|
|
|
|
testargs = """
|
|
run_language_modeling.py
|
|
--model_name_or_path distilroberta-base
|
|
--model_type roberta
|
|
--mlm
|
|
--line_by_line
|
|
--train_data_file ./tests/fixtures/sample_text.txt
|
|
--eval_data_file ./tests/fixtures/sample_text.txt
|
|
--output_dir ./tests/fixtures
|
|
--overwrite_output_dir
|
|
--do_train
|
|
--do_eval
|
|
--num_train_epochs=1
|
|
--no_cuda
|
|
""".split()
|
|
with patch.object(sys, "argv", testargs):
|
|
result = run_language_modeling.main()
|
|
self.assertLess(result["perplexity"], 35)
|
|
|
|
def test_run_squad(self):
|
|
stream_handler = logging.StreamHandler(sys.stdout)
|
|
logger.addHandler(stream_handler)
|
|
|
|
testargs = [
|
|
"run_squad.py",
|
|
"--data_dir=./examples/tests_samples/SQUAD",
|
|
"--model_name=bert-base-uncased",
|
|
"--output_dir=./examples/tests_samples/temp_dir",
|
|
"--max_steps=10",
|
|
"--warmup_steps=2",
|
|
"--do_train",
|
|
"--do_eval",
|
|
"--version_2_with_negative",
|
|
"--learning_rate=2e-4",
|
|
"--per_gpu_train_batch_size=2",
|
|
"--per_gpu_eval_batch_size=1",
|
|
"--overwrite_output_dir",
|
|
"--seed=42",
|
|
]
|
|
model_type, model_name = ("--model_type=bert", "--model_name_or_path=bert-base-uncased")
|
|
with patch.object(sys, "argv", testargs + [model_type, model_name]):
|
|
result = run_squad.main()
|
|
self.assertGreaterEqual(result["f1"], 30)
|
|
self.assertGreaterEqual(result["exact"], 30)
|
|
|
|
def test_generation(self):
|
|
stream_handler = logging.StreamHandler(sys.stdout)
|
|
logger.addHandler(stream_handler)
|
|
|
|
testargs = ["run_generation.py", "--prompt=Hello", "--length=10", "--seed=42"]
|
|
model_type, model_name = ("--model_type=openai-gpt", "--model_name_or_path=openai-gpt")
|
|
with patch.object(sys, "argv", testargs + [model_type, model_name]):
|
|
result = run_generation.main()
|
|
self.assertGreaterEqual(len(result[0]), 10)
|